CN110197119A - Travelling data analysis method, device, computer equipment and storage medium - Google Patents
Travelling data analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110197119A CN110197119A CN201910326600.XA CN201910326600A CN110197119A CN 110197119 A CN110197119 A CN 110197119A CN 201910326600 A CN201910326600 A CN 201910326600A CN 110197119 A CN110197119 A CN 110197119A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- frequency
- target vehicle
- driving
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application involves a kind of travelling data analysis method, device, computer equipment and storage medium based on big data.This method comprises: obtaining the travelling data of target vehicle;The travelling data includes driving image;Identification region is determined in the driving image;Identification vehicles identifications appear in vehicle near identification region, record the vehicle location of the vehicle nearby;By comparing the variation of the vehicle location of vehicle nearby in adjacent multiframe driving image, judge the target vehicle with the presence or absence of passing behavior;It is counted according to the overtake other vehicles frequency of the judging result to the target vehicle;The corresponding vehicle insurance expense of the target vehicle is calculated according to the frequency of overtaking other vehicles.Travelling data analysis efficiency can be improved using this method, then improve vehicle insurance expense computational efficiency.
Description
Technical field
This application involves field of computer technology, set more particularly to a kind of travelling data analysis method, device, computer
Standby and storage medium.
Background technique
As automobile is increasingly becoming universal walking-replacing tool, vehicle insurance market is also developed rapidly, and vehicle insurance business is in bright
The aobvious trend increased.In order to push vehicle insurance business development, a kind of UBI (Usage Based Insurance) insurance is newly risen.
UBI can be adjusted insurance premium in conjunction with travelling data is driven, and theoretically the safer user of driving behavior performance should
It is preferential to obtain premium.However, the driving behavior data for vehicle user collect and analyze the plenty of time with dependence on labor costs,
So that vehicle insurance expense computational efficiency reduces.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be improved travelling data analysis efficiency, then mention
Travelling data analysis method, device, computer equipment and the storage medium of high vehicle insurance expense computational efficiency.
A kind of travelling data analysis method, which comprises obtain the travelling data of target vehicle;The travelling data
Including image of driving a vehicle;Identification region is determined in the driving image;Identification vehicles identifications appear in vehicle near identification region
, record the vehicle location of the vehicle nearby;By comparing the vehicle location of neighbouring vehicle in adjacent multiframe driving image
Variation judges the target vehicle with the presence or absence of passing behavior;According to judging result to the target vehicle overtake other vehicles the frequency into
Row statistics;The corresponding vehicle insurance expense of the target vehicle is calculated according to the frequency of overtaking other vehicles.
In one embodiment, described that identification region is determined in the driving image, comprising: to identify the driving image
In identification starting point and lane sideline;Target vehicle and the following distance with lane front truck are obtained, it is true according to the following distance
Fixed identification distance;Identification region is determined based on identification starting point and identification distance.
In one embodiment, the vehicle location for recording the vehicle nearby, comprising: raw according to the identification distance
At respectively sideline;Identification region is divided into multiple subregions based on the respectively sideline and the lane sideline;Near
The position of subregion determines corresponding vehicle location where vehicle.
In one embodiment, by comparing the variation of the vehicle location of vehicle nearby in adjacent multiframe driving image, sentence
The target vehicle that breaks whether there is passing behavior, comprising: according to the vehicle location in adjacent multiframe driving image, generate attached
The driving feature vector of nearly vehicle;The first property value of the driving feature vector is calculated, whether is the first property value
Reach threshold value;If reaching threshold value, the second attribute value of the driving feature vector is calculated;Judge second attribute value whether be
Target Attribute values;If Target Attribute values, marking the target vehicle, there are passing behaviors.
In one embodiment, the travelling data includes running time;According to the vehicle in adjacent multiframe driving image
Position generates the driving feature vector of vehicle nearby, comprising: according to the running time, determines time of multiframe driving image
Go through sequence;According to the traversal order, successively traversed to whether every frame line vehicle image neighbouring vehicle occurs;By attachment vehicle
Vehicle location in a frame or multiframe driving image is respectively labeled as the vector element of different order;To each attachment vehicle
Adjacent vector element carries out duplicate removal processing;Based on multiple vector elements after duplicate removal generate the driving feature of corresponding vehicle nearby to
Amount.
In one embodiment, the travelling data further includes vehicle sensed data;The basis overtake other vehicles the frequency calculate institute
State the corresponding vehicle insurance expense of target vehicle, comprising: the deviation frequency based on target vehicle described in the driving image recognition
With the anti-collision warning frequency;The hypervelocity frequency and the zig zag frequency of the target vehicle are counted based on the vehicle sensed data;It climbs
Take the bad steering of the target vehicle to record, based on bad steering record count the target vehicle the drunk driving frequency and
The liability accident frequency;According to the frequency of overtaking other vehicles of statistical time range, the deviation frequency, the anti-collision warning frequency, the hypervelocity frequency, zig zag
The frequency, the drunk driving frequency and the liability accident frequency determine the driving behavior security level of the target vehicle;It is gone according to the driving
The vehicle insurance expense of the target vehicle is adjusted for security level.
A kind of travelling data analytical equipment, described device includes: driving image processing module, for obtaining target vehicle
Travelling data;The travelling data includes driving image;Identification region is determined in the driving image;Identification vehicles identifications go out
Vehicle near present identification region records the vehicle location of the vehicle nearby;Passing behavior analysis module, for passing through ratio
The variation of the vehicle location of vehicle nearby, judges the target vehicle with the presence or absence of row of overtaking other vehicles in more adjacent multiframe driving image
For;It is counted according to the overtake other vehicles frequency of the judging result to the target vehicle;Vehicle insurance expense computing module, for according to
The frequency of overtaking other vehicles calculates the corresponding vehicle insurance expense of the target vehicle.
The driving image processing module is also used to identify the identification in the driving image in one of the embodiments,
Starting point and lane sideline;Obtain target vehicle and following distance with lane front truck, according to the following distance determine identification away from
From;Identification region is determined based on identification starting point and identification distance.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step of travelling data analysis method provided in any one embodiment of the application when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of travelling data analysis method provided in any one embodiment of the application is provided when row.
Above-mentioned travelling data analysis method, device, computer equipment and storage medium, according to the more of the target vehicle of acquisition
Frame line vehicle image can determine the identification region in driving image;It is identified whether to appear in identification region, Ke Yishi according to license plate
The corresponding vehicle nearby of other target vehicle;It, can according to vehicle location of the vehicle near record in adjacent multiframe driving image
To compare the variation of vehicle location;According to the variation of vehicle location, it can be determined that the target vehicle whether there is passing behavior;
According to judging result, the frequency of overtaking other vehicles for obtaining the target vehicle can be counted;According to the frequency of overtaking other vehicles, can calculate described
The corresponding vehicle insurance expense of target vehicle.Due to carrying out the acquisition and analysis of travelling data automatically, and directly count based on the analysis results
Vehicle insurance expense is calculated, vehicle insurance expense computational efficiency not only can be improved, can also be improved calculated result objectivity and accuracy.This
Outside, by carrying out identification region division to driving image, and position statistics is carried out to neighbouring vehicle based on identification region, according to attached
The change in location of nearly vehicle relative target vehicle judges target vehicle with the presence or absence of passing behavior, compared to general movement images
Passing behavior judgment accuracy can be improved in similarity, and then improves vehicle insurance expense and calculate accuracy.
Detailed description of the invention
Fig. 1 is the application scenario diagram of one embodiment middle rolling car data analysing method;
Fig. 2 is the flow diagram of one embodiment middle rolling car data analysing method;
Fig. 3 A is a process schematic of one embodiment middle rolling car image procossing;
Fig. 3 B is another process schematic of one embodiment middle rolling car image procossing;
Fig. 3 C is the another process schematic of one embodiment middle rolling car image procossing;
Fig. 4 is the flow diagram for the step of passing behavior determines in one embodiment;
Fig. 5 is the structural block diagram of one embodiment middle rolling car data analysis set-up;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Travelling data analysis method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network.Wherein, terminal 102 can be, but not limited to be various personal computers, pen
Remember this computer, smart phone, tablet computer and portable wearable device, it is corresponding that terminal 102 can be target vehicle car owner
Terminal is also possible to the corresponding terminal of insurance company of target vehicle car owner vehicle insurance business to be handled.Server 104 can be with solely
The server clusters of the either multiple servers compositions of vertical server is realized.Vehicle insurance industry is handled when being desired based on target vehicle
When business, user can send vehicle insurance to server based on terminal 102 and handle request.Vehicle insurance handles request and carries target vehicle mark
Know.Server 104 identifies the travelling data for obtaining corresponding target vehicle according to target vehicle.Travelling data includes multiframe road map
Picture.Server 104 determines identification region in driving image, and identifies that vehicles identifications appear in the vehicle of identification region, will know
The marking of cars being clipped to is neighbouring vehicle.Server 104 records vehicle location of the neighbouring vehicle in adjacent multiframe driving image,
And compare the variation of vehicle location, it may determine that target vehicle with the presence or absence of passing behavior according to comparison result.Server 104
It is judged that result counts the frequency of overtaking other vehicles of target vehicle, the driving of target vehicle user may determine that according to the frequency of overtaking other vehicles
Behavioural habits safety further calculates the corresponding vehicle insurance expense of target vehicle according to the frequency of overtaking other vehicles.Server 104 will calculate
To vehicle insurance expense be back to terminal 102.Above-mentioned vehicle insurance expense calculating process, the automatic acquisition and analysis for carrying out travelling data,
And vehicle insurance expense is directly adjusted based on the analysis results, greatly reduce artificial burden, vehicle insurance expense computational efficiency not only can be improved,
It can also be improved vehicle insurance expense and calculate objectivity and accuracy.
In one embodiment, as shown in Fig. 2, providing a kind of travelling data analysis method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step 202, the travelling data of target vehicle is obtained;Travelling data includes driving image.
Server makes full use of the travelling data of automobile data recorder acquisition and recording, according to preset time frequency collection target carriage
Travelling data.Travelling data includes multiframe driving image and every frame line vehicle image corresponding running time.
Step 204, identification region is determined in driving image.
Certain area around target vehicle is determined as identification region in driving image by server.For example, can be by mesh
Mark right ahead, dead astern, at least the region of the preset area of side is identification region in left or right side.Preset area
It can be fixed value, be also possible to the dynamic values such as the preset ratio of driving image.
Step 206, identification vehicles identifications appear in vehicle near identification region, record the vehicle location of vehicle nearby.
Vehicles identifications can be license plate number etc..Identification region includes multiple subregions.Server is according to attachment vehicle
Which subregion of identification region, determines the vehicle location of each neighbouring vehicle.
Step 208, by comparing the variation of the vehicle location of vehicle nearby in adjacent multiframe driving image, judge target carriage
Whether there is passing behavior.
Adjacent multiframe can be the preset quantity frame number acquired recently, such as 3 frames.It is readily appreciated that, the frame of comparison driving image
Number can according to need free setting, without limitation.Some neighbouring vehicle license plate marks are in preset quantity frame line vehicle image
In may only framing in the middle driving image in occur.Each vehicle nearby is identified to only one equal vehicle position for the first time
It sets, as driving number of image frames increases, the vehicle location of storage is gradually increased, but at most only deposits preset quantity road location.
In other words, the quantity of the vehicle location of vehicle is less than or equal to preset quantity near each of storage.
Server obtains the variation tendency of each vehicle nearby vehicle location in multiframe driving image, judges that the variation becomes
Whether gesture is the first preset trend.If so, server determines target vehicle, in corresponding running time, there are passing behaviors.
Step 210, it is counted according to the overtake other vehicles frequency of the judging result to target vehicle.
According to judging result, the overtake other vehicles frequency of the server to target vehicle in statistical time range is counted.Statistical time range can
To be that target vehicle car owner initiates a period of time before vehicle insurance handles request, such as half a year.The frequency of overtaking other vehicles, which can be, overtakes other vehicles time
Several ratios with statistical time range time span.
In another embodiment, number of the server to target vehicle in statistical time range passed vehicle (is denoted as passed vehicle time
Number) it is counted.For example, server judges nearby whether vehicle variation tendency of vehicle location in multiframe driving image is pre-
If second of trend.If so, server determines target vehicle, in corresponding running time, there are passed vehicle behaviors.At this point, overtaking other vehicles
The calculating of the frequency may is that the frequency of overtaking other vehicles=number of overtaking other vehicles/(number of overtaking other vehicles+passed vehicle number).
Step 212, the corresponding vehicle insurance expense of target vehicle is calculated according to the frequency of overtaking other vehicles.
Server can preset a variety of corresponding vehicle insurance expense adjustment in frequency section and every kind of frequency section of overtaking other vehicles of overtaking other vehicles
Ratio.Server determines that target vehicle is overtaken other vehicles frequency section of overtaking other vehicles belonging to the frequency, according to the corresponding vehicle in frequency section of overtaking other vehicles
Dangerous expense adjustment ratio increases or reduces basic vehicle insurance expense, obtains the corresponding vehicle expense of target vehicle.
In the present embodiment, according to the multiframe of the target vehicle of acquisition driving image, the identification in driving image can be determined
Region;It is identified whether to appear in identification region according to license plate, can identify the corresponding vehicle nearby of target vehicle;According to record
Vehicle location of the neighbouring vehicle in adjacent multiframe driving image, can compare the variation of vehicle location;According to vehicle location
Variation, it can be determined that target vehicle whether there is passing behavior;According to judging result, can count to obtain overtaking other vehicles for target vehicle
The frequency;According to the frequency of overtaking other vehicles, the corresponding vehicle insurance expense of target vehicle can be calculated.Due to carry out automatically travelling data acquisition and
Analysis, and vehicle insurance expense is directly calculated based on the analysis results, vehicle insurance expense computational efficiency not only can be improved, can also be improved meter
Calculate result objectivity and accuracy.In addition, by carrying out identification region division to driving image, and based on identification region near
Vehicle carries out position statistics, judges that target vehicle whether there is according to the change in location of neighbouring vehicle relative target vehicle and overtakes other vehicles
Behavior can be improved passing behavior judgment accuracy compared to general movement images similarity, and then improve vehicle insurance expense and calculate
Accuracy.
In one embodiment, the step of determining identification region in image of driving a vehicle, comprising: the knowledge in identification driving image
Other starting point and lane sideline;Target vehicle and the following distance with lane front truck are obtained, identification distance is determined according to following distance;
Identification region is determined based on identification starting point and identification distance.
Automobile data recorder is usually the vehicle condition and road conditions acquired around target vehicle centered on target vehicle, is thus serviced
Device can be by the position (i.e. target vehicle position) for the image lower middle side that drives a vehicle labeled as identification starting point.On pavement of road
Would generally there are lines, arrow, text, object marking, protuberant guide post and delineator etc. for guiding to traffic participant transmitting, limit
The traffic marking of the traffic informations such as system, warning.Wherein, lane sideline, which refers to, divides vehicle in the user where target vehicle on road
The lines in road.
If target vehicle exists with lane front truck in image of driving a vehicle, server obtains target vehicle distance with lane front truck
Image distance calculates the following distance of target range according to image distance and image taking ratio.If target in image of driving a vehicle
Vehicle is not present with lane front truck, then server obtains image taking distance, according to image taking distance and image taking ratio
Example, calculates the following distance of target range.Server carries out logic of propositions operation to following distance, obtains identification distance.For example,
Following distance * 3/2=identifies distance.In another embodiment, can the drive a vehicle preset ratio of image of identification distance is moved
State determines, is also possible to fixed value, without limitation.
Identification region can be the quadrangle that side length is determined according to preset length and identification distance.Wherein, identification starting point is
The midpoint on a side in quadrangle.Fig. 3 A is the wherein 1 frame line vehicle image that the automobile data recorder of target vehicle is shot.Such as Fig. 3 A institute
Show, which can be to identify that starting point is the isosceles trapezoid of following terminal, wherein lower edge lengths
It can be image lane width * 3 respectively with upper edge lengths, highly can be identification distance.Image lane width can be one
Width of the lane in driving image.It is readily appreciated that, in the different images height of driving image, corresponding image lane width is not
Together.For example, the image lane width of picture altitude can be 5cm where following;The image lane of picture altitude is wide where top
Degree can be 3cm.
Server identifies vehicle near target vehicle in driving image.In the example above, exist in identification region
Five vehicles, wherein can recognize license plate mark have A, B, C and D tetra-, although vehicle E can recognize its license plate mark
Know, but it is in identification region, so that vehicle includes A, B, C and D near target vehicle.
In the present embodiment, image procossing is carried out to driving image, is dynamically determined target vehicle in the knowledge of each driving image
Other region selects mode that region division accuracy can be improved compared to general frame;Dynamic limitation is carried out to identification region, it can be right
It needs the content of further detail image processing precisely to be limited, not only improves accuracy of identification, need image due to having limited
The data volume of processing, can also be improved recognition efficiency.
In one embodiment, the vehicle location of vehicle nearby is recorded, comprising: generate according to identification distance and divide equally sideline;
Identification region is divided into multiple subregions based on respectively sideline and lane sideline;According to the position of subregion where neighbouring vehicle
Determine corresponding vehicle location.
Different according to the number for dividing equally identification region, respectively the quantity in sideline is different.For example, the respectively quantity in sideline
It can be the number -1 for dividing equally identification region.The length that difference divides equally sideline can be different.Respectively the length in sideline can also
To be the integral multiple of image lane width * 3.For example, after carrying out region division to the driving image of the example above, it is available such as
Image shown in Fig. 3 B.In figure 3b, server is according to identification distance by identification region trisection.Specifically, server according to
Number identification distance and divide equally identification region generates three and divides equally sideline.Wherein, respectively the length in sideline 1 can be with
It is image lane width * 3, respectively sideline 2 and the length in respectively sideline 3 can be image lane width * 1 respectively.
Server can construct coordinate system based on identification region, and then determine that divide equally sideline and lane sideline is expert at respectively
The image coordinate of vehicle image.Server spells a plurality of respectively sideline and lane sideline in identification region according to image coordinate
It connects, and then identification region is divided into multiple subregions, and the coordinate position according to subregion in a coordinate system, by multiple difference
Labeled as upper region, middle region or lower region.As shown in Figure 3 C, in the example above, identification region is divided into 6 sons by server
The maximum subregion 1 of ordinate is labeled as upper region by region, and by ordinate time height and identical subregion 2 and subregion 3 divide
It Biao Ji not be region, it is ordinate is minimum and identical subregion 5 and subregion 6 are respectively labeled as lower region.It is readily appreciated that,
It is lower than 3 parts to the number for dividing equally identification region, then it is different that certain sub-regions can be further broken into multiple ordinates
Intermediate region after according still further to aforesaid way be divided into three kinds of upper, middle and lower region.It is more than to the number for dividing equally identification region
3 parts, then can be merged into behind an intermediate region with the adjacent subregion of multiple ordinates be divided into according still further to aforesaid way,
In, lower three kinds of regions.
According to the position of subregion where neighbouring vehicle, server can determine corresponding vehicle location.For example, neighbouring vehicle
The vehicles identifications of A appear in region, then it is upper for can recorde the vehicle location of neighbouring vehicle.In another embodiment,
The vehicle location of neighbouring vehicle can be specific coordinate of the vehicles identifications in identification region respective coordinates system of neighbouring vehicle A, right
This is with no restriction.
It is worth noting that, identification region can also be determined using other modes, it can also be using other modes to knowledge
Other region is divided, and the present embodiment is merely given as can determine the one of the vehicle location variation of neighbouring vehicle relative target vehicle
Kind exemplary instrumentation.
In the present embodiment, identification region is further divided into convenient for determining vehicle relative target vehicle location variation nearby
Multiple subregions, multiple subregions based on this model split, can simplify identification nearby vehicle relative target vehicle position
The recognizer of variation tendency is set, and then improves passing behavior analysis efficiency.
In one embodiment, as shown in figure 4, by comparing adjacent multiframe driving image in nearby vehicle vehicle location
Variation, judge target vehicle with the presence or absence of passing behavior, i.e., the step of passing behavior determines, comprising:
Step 402, according to adjacent multiframe driving image in vehicle location, generate nearby vehicle driving feature to
Amount.
In one embodiment, travelling data includes running time;According to the vehicle position in adjacent multiframe driving image
It sets, generates the driving feature vector of vehicle nearby, comprising: according to running time, determine the traversal order of multiframe driving image;Root
According to traversal order, successively traversed to whether every frame line vehicle image neighbouring vehicle occurs;By attachment vehicle in a frame or multiframe
Vehicle location in driving image is respectively labeled as the vector element of different order;To the adjacent vector element of each attachment vehicle
Carry out duplicate removal processing.The driving feature vector of corresponding vehicle nearby is generated based on multiple vector elements after duplicate removal.
Server traverses collected multiframe driving image according to the sequencing of running time.It is readily appreciated that,
Some neighbouring vehicles acquire recently multiframe driving image in may only framing in the middle driving image in occur.Therefore,
Server judges that the license plate mark of vehicle nearby whether there is in the first frame driving image of acquisition in ergodic process.If
Exist in first frame driving image, vehicle position mark of the attachment vehicle in first frame driving image is first by server
The vector element of sequence.Server continues to judge whether the license plate mark of neighbouring vehicle deposits in the next frame driving image of acquisition
?.If existing in next frame driving image, vehicle position mark of the attachment vehicle in next frame driving image is by server
Whether the vector element of next sequence, the license plate mark for continuing vehicle near Ergodic judgement deposit in the driving image of next frame again
It is so repeating to traverse, the image until last frame is driven a vehicle, is obtaining each corresponding multiple vector elements of vehicle nearby.Under if
It is not present in one frame line vehicle image, server continues traversal next frame driving image again in the manner described above.
According to the acquisition of vector element sequence, multiple vector elements are ranked up by server, formation element queue.Service
Device judges whether each vector element repeats with previous vector element in element queues.If repeating, server will be corresponded to
Vector element deleted from element queues, based on the element queues after duplicate removal generate the driving feature of corresponding vehicle nearby to
Amount.For example, in the example above, the corresponding driving feature vector of neighbouring vehicle A can be [on, in, under], B pairs of neighbouring vehicle
The driving feature vector answered can be [under, in, on], and the corresponding driving feature vector of neighbouring vehicle C can be [on, in], attached
The corresponding driving feature vector of nearly vehicle D can be [in, under].It is readily appreciated that, there is no similar presence such as [in, under, under]
The duplicate driving feature vector of adjacent vector element.
Step 404, the first property value for calculating driving feature vector, compares whether first property value reaches threshold value.
First property value can be the quantity that driving feature vector includes vector element.Threshold value can be fixed value, and such as 3.
Threshold value is also possible to according to the numerical value for being dynamically determined the number that image is divided equally of driving a vehicle.
Step 406, if reaching threshold value, the second attribute value of driving feature vector is calculated.
If the first property value for feature vector of driving a vehicle is less than threshold value, whether the relatively corresponding vehicle nearby of server target vehicle
Generation passing behavior, which is not done, to be determined.For example, the first property value of neighbouring vehicle C and neighbouring vehicle D are 2, small in the example above
In threshold value 3.
If the first property value for feature vector of driving a vehicle is equal to threshold value, server, which further calculates, drives a vehicle the of feature vector
Two attribute values.Second attribute value can be the category of the variation tendency of the vehicle location for characterizing neighbouring vehicle relative target vehicle
Property value.
Step 408, judge whether the second attribute value is Target Attribute values.
Step 410, if Target Attribute values, marking target vehicle, there are passing behaviors.
Server has preset plurality of target attribute value and the associated judgement result of every kind of Target Attribute values.For example, upper
It states in citing, corresponding second attribute value of neighbouring vehicle A is Target Attribute values 3, indicates target vehicle relatively nearby vehicle A preceding
Into, it is possible to determine that nearby passing behavior occurs target vehicle for vehicle A relatively.
In the present embodiment, passing behavior parser is simplified, passes through the first property value to driving feature vector
Whether meet corresponding preset condition respectively with the second attribute value, that is, can determine whether target vehicle occurs passing behavior, improves
Passing behavior analysis efficiency.
In one embodiment, the corresponding vehicle insurance expense of target vehicle is calculated according to the frequency of overtaking other vehicles, comprising: be based on road map
As the deviation frequency and the anti-collision warning frequency of identification target vehicle;Hypervelocity based on vehicle sensed data statistics target vehicle
The frequency and the zig zag frequency;The bad steering record for crawling target vehicle, the wine of statistics target vehicle is recorded based on bad steering
Drive the frequency and the liability accident frequency;According to the frequency of overtaking other vehicles of statistical time range, the deviation frequency, the anti-collision warning frequency, hypervelocity frequency
Secondary, the zig zag frequency, the drunk driving frequency and the liability accident frequency, determine the driving behavior security level of target vehicle;According to driving
The vehicle insurance expense of behavior safety level adjustment target vehicle.
Server judges mesh by comparing the change in location in target vehicle opposite lane sideline in adjacent multiframe driving image
Marking vehicle whether there is deviation behavior.When there are deviation behavior, deviation frequency of the server to target vehicle
It is secondary to be counted.Whether server is less than preset value by comparing following distance, judges target vehicle with the presence or absence of anti-collision warning
Behavior, when there are anti-collision warning behavior, server counts the anti-collision warning frequency of target vehicle.
Travelling data further includes vehicle sensed data.Vehicle sensed data includes speed change data and direction change number
According to.Server obtains corresponding roadway speed limit data according to driving image, is become based on roadway speed limit data and speed
Change data, judges target vehicle with the presence or absence of hypervelocity behavior.Exceed the speed limit behavior if it exists, the hypervelocity frequency of the server to target vehicle
It is counted.Server judges target vehicle with the presence or absence of zig zag behavior according to direction change data.Zig zag row if it exists
For server counts the zig zag frequency of target vehicle.
Server crawls the bad steering record of target vehicle in traffic administration website etc..Bad steering record includes drunk driving
Record, bear all the responsibilities or the traffic accident of part responsibility record etc..Server records the wine of statistics target vehicle based on bad steering
Drive the frequency and the liability accident frequency.
Server is according to target vehicle in the frequency of overtaking other vehicles of statistical time range, the deviation frequency, the anti-collision warning frequency, hypervelocity
Safety evaluation index and the preset different dimensional of the frequency, the take a sudden turn frequency, the drunk driving frequency and the multiple dimensions of the liability accident frequency
The corresponding index weights of safety evaluation index are spent, the driving behavior security level of determining target vehicle can be integrated.According to driving
Behavior safety grade, the vehicle insurance expense of adjustable target vehicle.For example, based on the different corresponding different guarantors of frequency setting that overtake other vehicles
Take discount rate.
In the present embodiment, based on the frequency of overtaking other vehicles, the deviation frequency, the anti-collision warning frequency, the hypervelocity frequency, zig zag frequency
The safety evaluation index of secondary, the drunk driving frequency and the multiple dimensions of the liability accident frequency determines driving behavior safety of target vehicle etc.
Grade can be improved driving behavior security level and calculate accuracy, and then improves vehicle insurance expense and calculate accuracy.
It should be understood that although each step in the flow chart of Fig. 2 and Fig. 4 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, in Fig. 2 and Fig. 4
At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily
It is successively to carry out, but in turn or can be handed over at least part of the sub-step or stage of other steps or other steps
Alternately execute.
In one embodiment, as shown in figure 5, providing a kind of travelling data analytical equipment, comprising: driving image procossing
Module 502, passing behavior analysis module 504 and vehicle insurance expense computing module 506, in which:
Driving image processing module 502, for obtaining the travelling data of target vehicle;Travelling data includes driving image;
Identification region is determined in driving image;Identification vehicles identifications appear in vehicle near identification region, vehicle near record
Vehicle location.
Passing behavior analysis module 504, for the vehicle location by comparing neighbouring vehicle in adjacent multiframe driving image
Variation, judge target vehicle with the presence or absence of passing behavior;It is counted according to the overtake other vehicles frequency of the judging result to target vehicle.
Vehicle insurance expense computing module 506, for calculating the corresponding vehicle insurance expense of target vehicle according to the frequency of overtaking other vehicles.
In one embodiment, driving image processing module 502 is also used to identify identification starting point and vehicle in driving image
Road sideline;Target vehicle and the following distance with lane front truck are obtained, identification distance is determined according to following distance;Based on identifying
Point and identification distance determine identification region.
In one embodiment, driving image processing module 502, which is also used to be generated according to identification distance, divides equally sideline;It is based on
Respectively identification region is divided into multiple subregions by sideline and lane sideline;It is determined according to the position of subregion where neighbouring vehicle
Corresponding vehicle location.
In one embodiment, passing behavior analysis module 504 is also used to according to the vehicle in adjacent multiframe driving image
Position generates the driving feature vector of vehicle nearby;The first property value for calculating driving feature vector, compares first property value
Whether threshold value is reached;If reaching threshold value, the second attribute value of driving feature vector is calculated;Judge whether the second attribute value is target
Attribute value;If Target Attribute values, marking target vehicle, there are passing behaviors.
In one embodiment, travelling data includes running time;Passing behavior analysis module 504 is also used to according to driving
Time determines the traversal order of multiframe driving image;According to traversal order, successively whether there is neighbouring vehicle to every frame line vehicle image
It is traversed;Vehicle location of the attachment vehicle in a frame or multiframe driving image is respectively labeled as to the vector of different order
Element;Duplicate removal processing is carried out to the adjacent vector element of each attachment vehicle;Phase is generated based on multiple vector elements after duplicate removal
Answer the driving feature vector of vehicle nearby.
In one embodiment, travelling data further includes vehicle sensed data;Vehicle insurance expense computing module 506 is also used to base
In the deviation frequency and the anti-collision warning frequency of driving image recognition target vehicle;Target carriage is counted based on vehicle sensed data
The hypervelocity frequency and zig zag the frequency;The bad steering record for crawling target vehicle, based on bad steering record statistics target
The drunk driving frequency and the liability accident frequency of vehicle;According to the frequency of overtaking other vehicles, the deviation frequency, anti-collision warning of statistical time range frequency
Secondary, the hypervelocity frequency, the zig zag frequency, the drunk driving frequency and the liability accident frequency, determine the driving behavior security level of target vehicle;
The vehicle insurance expense of target vehicle is adjusted according to driving behavior security level.
Specific about travelling data analytical equipment limits the limit that may refer to above for travelling data analysis method
Fixed, details are not described herein.Modules in above-mentioned travelling data analytical equipment can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the travelling data of target vehicle.The network interface of the computer equipment is used for and exterior terminal
It is communicated by network connection.To realize a kind of travelling data analysis method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
A kind of computer readable storage medium is stored thereon with computer program, when computer program is executed by processor
The step of travelling data analysis method provided in any one embodiment of the application is provided.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
Non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, description more it is specific in detail, but can not be because
This is construed as limiting the scope of the patent.It should be pointed out that those skilled in the art, not departing from this
Under the premise of application design, various modifications and improvements can be made, these belong to the protection scope of the application.Therefore, originally
Apply for a patent that the scope of protection shall be subject to the appended claims.
Claims (10)
1. a kind of travelling data analysis method, which comprises
Obtain the travelling data of target vehicle;The travelling data includes driving image;
Identification region is determined in the driving image;
Identification vehicles identifications appear in vehicle near identification region, record the vehicle location of the vehicle nearby;
By comparing the variation of the vehicle location of vehicle nearby in adjacent multiframe driving image, judge whether the target vehicle is deposited
In passing behavior;
It is counted according to the overtake other vehicles frequency of the judging result to the target vehicle;
The corresponding vehicle insurance expense of the target vehicle is calculated according to the frequency of overtaking other vehicles.
2. the method according to claim 1, wherein described determine identification region, packet in the driving image
It includes:
Identify the identification starting point in the driving image and lane sideline;
Target vehicle and the following distance with lane front truck are obtained, identification distance is determined according to the following distance;
Identification region is determined based on identification starting point and identification distance.
3. according to the method described in claim 2, it is characterized in that, the vehicle location for recording the vehicle nearby, comprising:
It is generated according to the identification distance and divides equally sideline;
Identification region is divided into multiple subregions based on the respectively sideline and the lane sideline;
Corresponding vehicle location is determined according to the position of subregion where neighbouring vehicle.
4. the method according to claim 1, wherein by comparing neighbouring vehicle in adjacent multiframe driving image
The variation of vehicle location judges the target vehicle with the presence or absence of passing behavior, comprising:
According to the vehicle location in adjacent multiframe driving image, the driving feature vector of vehicle nearby is generated;
The first property value of the driving feature vector is calculated, whether the first property value reaches threshold value;
If reaching threshold value, the second attribute value of the driving feature vector is calculated;
Judge whether second attribute value is Target Attribute values;
If Target Attribute values, marking the target vehicle, there are passing behaviors.
5. according to the method described in claim 4, it is characterized in that, the travelling data includes running time;According to adjacent
Vehicle location in multiframe driving image, generates the driving feature vector of vehicle nearby, comprising:
According to the running time, the traversal order of multiframe driving image is determined;
According to the traversal order, successively traversed to whether every frame line vehicle image neighbouring vehicle occurs;
Vehicle location of the attachment vehicle in a frame or multiframe driving image is respectively labeled as to the vector element of different order;
Duplicate removal processing is carried out to the adjacent vector element of each attachment vehicle;
The driving feature vector of corresponding vehicle nearby is generated based on multiple vector elements after duplicate removal.
6. the method according to claim 1, wherein the travelling data further includes vehicle sensed data;It is described
The corresponding vehicle insurance expense of the target vehicle is calculated according to the frequency of overtaking other vehicles, comprising:
The deviation frequency and the anti-collision warning frequency based on target vehicle described in the driving image recognition;
The hypervelocity frequency and the zig zag frequency of the target vehicle are counted based on the vehicle sensed data;
The bad steering record for crawling the target vehicle, the drunk driving of the target vehicle is counted based on bad steering record
The frequency and the liability accident frequency;
According to the frequency of overtaking other vehicles of statistical time range, the deviation frequency, the anti-collision warning frequency, the hypervelocity frequency, the zig zag frequency, drunk driving
The frequency and the liability accident frequency determine the driving behavior security level of the target vehicle;
The vehicle insurance expense of the target vehicle is adjusted according to the driving behavior security level.
7. a kind of travelling data analytical equipment, described device include:
Driving image processing module, for obtaining the travelling data of target vehicle;The travelling data includes driving image;Institute
It states in driving image and determines identification region;Identification vehicles identifications appear in vehicle near identification region, record the vehicle nearby
Vehicle location;
Passing behavior analysis module, for by comparing adjacent multiframe driving image in nearby vehicle vehicle location variation,
Judge the target vehicle with the presence or absence of passing behavior;It is united according to the overtake other vehicles frequency of the judging result to the target vehicle
Meter;
Vehicle insurance expense computing module calculates the corresponding vehicle insurance expense of the target vehicle for the frequency of overtaking other vehicles according to.
8. device according to claim 7, which is characterized in that the driving image processing module is also used to identify the row
Identification starting point and lane sideline in vehicle image;Target vehicle and the following distance with lane front truck are obtained, according to the follow the bus
Distance determines identification distance;Identification region is determined based on identification starting point and identification distance.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910326600.XA CN110197119B (en) | 2019-04-23 | 2019-04-23 | Driving data analysis method, device, computer equipment and storage medium |
PCT/CN2019/118075 WO2020215690A1 (en) | 2019-04-23 | 2019-11-13 | Driving data analysis method and apparatus, and computer device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910326600.XA CN110197119B (en) | 2019-04-23 | 2019-04-23 | Driving data analysis method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110197119A true CN110197119A (en) | 2019-09-03 |
CN110197119B CN110197119B (en) | 2023-07-11 |
Family
ID=67752090
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910326600.XA Active CN110197119B (en) | 2019-04-23 | 2019-04-23 | Driving data analysis method, device, computer equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110197119B (en) |
WO (1) | WO2020215690A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111274931A (en) * | 2020-01-19 | 2020-06-12 | 上海眼控科技股份有限公司 | Overtaking behavior auditing method and device, computer equipment and storage medium |
WO2020215690A1 (en) * | 2019-04-23 | 2020-10-29 | 平安科技(深圳)有限公司 | Driving data analysis method and apparatus, and computer device and storage medium |
CN113034587A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle positioning method and device, computer equipment and storage medium |
TWI757964B (en) * | 2020-01-31 | 2022-03-11 | 神達數位股份有限公司 | Driving warning method and system and computer program product |
US11383733B2 (en) | 2020-01-31 | 2022-07-12 | Mitac Digital Technology Corporation | Method and system for detecting a dangerous driving condition for a vehicle, and non-transitory computer readable medium storing program for implementing the method |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112489450B (en) * | 2020-12-21 | 2022-07-08 | 阿波罗智联(北京)科技有限公司 | Traffic intersection vehicle flow control method, road side equipment and cloud control platform |
CN114022765B (en) * | 2021-11-03 | 2022-07-08 | 应急管理部国家自然灾害防治研究院 | Intelligent monitoring and early warning method and system for landslide, collapse and rockfall by adopting image recognition |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013074867A2 (en) * | 2011-11-16 | 2013-05-23 | Flextronics Ap, Llc | Insurance tracking |
US20140002656A1 (en) * | 2012-06-29 | 2014-01-02 | Lg Innotek Co., Ltd. | Lane departure warning system and lane departure warning method |
CN104118380A (en) * | 2013-04-26 | 2014-10-29 | 富泰华工业(深圳)有限公司 | Running vehicle detection system and method |
CN107618512A (en) * | 2017-08-23 | 2018-01-23 | 清华大学 | Driving behavior safe evaluation method based on people's car environment multi-data source |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130166325A1 (en) * | 2011-12-23 | 2013-06-27 | Mohan Ganapathy | Apparatuses, systems and methods for insurance quoting |
CN110197119B (en) * | 2019-04-23 | 2023-07-11 | 平安科技(深圳)有限公司 | Driving data analysis method, device, computer equipment and storage medium |
-
2019
- 2019-04-23 CN CN201910326600.XA patent/CN110197119B/en active Active
- 2019-11-13 WO PCT/CN2019/118075 patent/WO2020215690A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013074867A2 (en) * | 2011-11-16 | 2013-05-23 | Flextronics Ap, Llc | Insurance tracking |
US20140002656A1 (en) * | 2012-06-29 | 2014-01-02 | Lg Innotek Co., Ltd. | Lane departure warning system and lane departure warning method |
CN104118380A (en) * | 2013-04-26 | 2014-10-29 | 富泰华工业(深圳)有限公司 | Running vehicle detection system and method |
CN107618512A (en) * | 2017-08-23 | 2018-01-23 | 清华大学 | Driving behavior safe evaluation method based on people's car environment multi-data source |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020215690A1 (en) * | 2019-04-23 | 2020-10-29 | 平安科技(深圳)有限公司 | Driving data analysis method and apparatus, and computer device and storage medium |
CN113034587A (en) * | 2019-12-25 | 2021-06-25 | 沈阳美行科技有限公司 | Vehicle positioning method and device, computer equipment and storage medium |
CN113034587B (en) * | 2019-12-25 | 2023-06-16 | 沈阳美行科技股份有限公司 | Vehicle positioning method, device, computer equipment and storage medium |
CN111274931A (en) * | 2020-01-19 | 2020-06-12 | 上海眼控科技股份有限公司 | Overtaking behavior auditing method and device, computer equipment and storage medium |
TWI757964B (en) * | 2020-01-31 | 2022-03-11 | 神達數位股份有限公司 | Driving warning method and system and computer program product |
US11383733B2 (en) | 2020-01-31 | 2022-07-12 | Mitac Digital Technology Corporation | Method and system for detecting a dangerous driving condition for a vehicle, and non-transitory computer readable medium storing program for implementing the method |
Also Published As
Publication number | Publication date |
---|---|
WO2020215690A1 (en) | 2020-10-29 |
CN110197119B (en) | 2023-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110197119A (en) | Travelling data analysis method, device, computer equipment and storage medium | |
CN112396862B (en) | Parking management method and device | |
CN110032181B (en) | Method and device for positioning barrier in semantic map, computer equipment and storage medium | |
CN110838239A (en) | Parking space navigation method and device, computer readable storage medium and computer equipment | |
US20230154210A1 (en) | Method for recognizing license plate characters, electronic device and storage medium | |
CN110163248B (en) | Visualization method, visualization device, computer equipment and storage medium for model evaluation | |
CN112509364B (en) | Method and device for determining parking state of vehicle, computer equipment and storage medium | |
CN112734219B (en) | Vehicle transportation running behavior analysis method and system | |
CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
CN110751828A (en) | Road congestion measuring method and device, computer equipment and storage medium | |
CN109800984B (en) | Driving level evaluation method, driving level evaluation device, computer device, and storage medium | |
CN109615904A (en) | Parking management method, device, computer equipment and storage medium | |
CN111091215B (en) | Vehicle identification method, device, computer equipment and storage medium | |
DE102011001037A1 (en) | In-vehicle device for white line detection | |
WO2024067210A1 (en) | Traffic state determination method and apparatus, and device | |
CN111243185A (en) | Charging parking space occupation determination method, device and medium | |
CN115035744B (en) | Vehicle identification method, device and system based on image analysis and RFID | |
CN111292526A (en) | Method and device for adjusting vehicle driving restriction strategy, server and storage medium | |
EP2549408A1 (en) | Method for detecting and classifying objects | |
CN117115801A (en) | License plate authenticity identification method, device, equipment and storage medium | |
CN113095345A (en) | Data matching method and device and data processing equipment | |
CN114547403A (en) | Method, device and equipment for acquiring lane change scene and storage medium | |
CN114529778A (en) | Data enhancement method, device, equipment and storage medium | |
CN114463990A (en) | High-order video vehicle and license plate detection method and device | |
KR101980377B1 (en) | Buffer management based License Plate Recognition system for a refueling station |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |